create-skill

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's required Workflow step 1 instructs the agent to use WebFetch to fetch and read the latest spec from the public site https://agentskills.io, meaning the agent ingests untrusted third-party webpage content that directly informs how it should format frontmatter and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using WebFetch at runtime to retrieve the spec from https://agentskills.io, and that fetched content is required and used to determine the SKILL.md frontmatter and authoring instructions, so the external URL directly controls prompts/instructions.